Intelligent power control method and device for orthopedic surgery robot
By obtaining bone medical images and detecting bone density, determining osteotomy planning information, controlling the end power device of orthopedic surgical robot to perform bone cutting tests, solving the problem of low control accuracy of orthopedic surgical robots and achieving accurate control under different bone density .
Patent Information
- Application Number
- CN202411042133.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-29
AI Technical Summary
During the osteotomy process, due to the unbalanced bone density distribution of orthopedic surgical robots, the control accuracy is low, and the specific progress of orthopedic surgical robots cannot be accurately controlled.
By obtaining bone medical images, detecting bone density, determining osteotomy planning information based on preoperative planning schemes and bone density, controlling the terminal power device to perform osteotomy tests, and adjusting osteotomy planning information based on real-time data until the osteotomy test is completed.
Active control at different bone density is achieved, the accuracy of osteotomy control is improved, and the problem that hysteresis pendulum saw control cannot accurately control the specific progress of orthopedic surgical robots is avoided.
Smart Images

Figure CN119033467A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image processing technology, and in particular to an intelligent power control method and device for an orthopedic surgical robot. Background Art
[0002] Surgical robots are a combination of many modern high-tech means. They are widely used and have a large number of clinical applications. With the vigorous development of medical robot technology, surgical robots have been widely used as intelligent assistants. Knee replacement by surgical robots is a new technology for treating knee diseases that has gradually developed in modern times. It can effectively eradicate late-stage knee pain and greatly improve the quality of life of patients. It is more popular in developed countries and is currently in a stage of rapid development in China.
[0003] When current orthopedic surgical robots are performing actual osteotomies, the osteotomy torque of the oscillating saw changes constantly due to the uneven density distribution of the bones, making it impossible to accurately control the specific progress of the orthopedic surgical robot. Summary of the invention
[0004] The problem that this application solves is that the current orthopedic surgical robots have low control accuracy due to the density distribution of bones.
[0005] In order to solve the above problems, the first aspect of the present application provides an intelligent power control method for an orthopedic surgical robot, comprising:
[0006] Acquiring a skeletal medical image of any subject;
[0007] Determine a preoperative planning scheme according to the skeletal medical image, and detect the bone density of the skeletal medical image;
[0008] Determining osteotomy planning information based on the preoperative planning scheme and the bone density;
[0009] According to the osteotomy planning information, controlling the end power device of the orthopedic surgical robot to perform a osteotomy test;
[0010] Obtain real-time data of the end power device during bone cutting test;
[0011] The osteotomy planning information is adjusted according to the real-time data until the osteotomy test is completed.
[0012] The second aspect of the present application provides an intelligent power control device for an orthopedic surgical robot, comprising:
[0013] An image acquisition module, which is used to acquire a bone medical image of any object;
[0014] A preoperative planning module, which is used to determine a preoperative planning scheme according to the skeletal medical image and detect the bone density of the skeletal medical image;
[0015] An osteotomy planning module, which is used to determine osteotomy planning information based on the preoperative planning scheme and the bone density;
[0016] A bone cutting test module, which is used to control the end power device of the orthopedic surgical robot to perform a bone cutting test according to the osteotomy planning information;
[0017] The real-time adjustment module is used to obtain real-time data of the end power device during the bone cutting test; and adjust the bone cutting planning information according to the real-time data until the bone cutting test is completed.
[0018] A third aspect of the present application provides an electronic device, comprising: a memory and a processor;
[0019] The memory is used to store programs;
[0020] The processor, coupled to the memory, is configured to execute the program to:
[0021] Acquiring a skeletal medical image of any subject;
[0022] Determine a preoperative planning scheme according to the skeletal medical image, and detect the bone density of the skeletal medical image;
[0023] Determining osteotomy planning information based on the preoperative planning scheme and the bone density;
[0024] According to the osteotomy planning information, controlling the end power device of the orthopedic surgical robot to perform a osteotomy test;
[0025] Obtain real-time data of the end power device during bone cutting test;
[0026] The osteotomy planning information is adjusted according to the real-time data until the osteotomy test is completed.
[0027] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the above-mentioned intelligent power control method for an orthopedic surgical robot.
[0028] In this application, the bone density of the skeletal medical image is used to determine the bone density distribution on the osteotomy path, so that the corresponding osteotomy planning data is pre-set based on the bone density to avoid the lagging swing saw control that cannot accurately control the specific progress of the orthopedic surgical robot. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Figure 1is a flow chart of an intelligent power control method for an orthopedic surgical robot according to an embodiment of the present application;
[0030] Figure 2 A schematic diagram of a bone cutting test of an orthopedic surgical robot intelligent power control method according to an embodiment of the present application;
[0031] Figure 3 This is a flow chart of bone density detection of the intelligent power control method of an orthopedic surgical robot according to an embodiment of the present application;
[0032] Figure 4 A flowchart of an example of an intelligent power control method for an orthopedic surgical robot according to an embodiment of the present application;
[0033] Figure 5 This is a schematic diagram of the bone density detection of the orthopedic surgical robot intelligent power control method according to an embodiment of the present application;
[0034] Figure 6 A partial architecture diagram of bone density detection of an orthopedic surgical robot intelligent power control method according to an embodiment of the present application;
[0035] Figure 7 is a structural block diagram of an intelligent power control device for an orthopedic surgical robot according to an embodiment of the present application;
[0036] Figure 8 is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION
[0037] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application are described in detail below in conjunction with the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.
[0038] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by technicians in the field to which this application belongs.
[0039] In knee replacement surgery, one of the key steps is to use an oscillating saw to remove the original bad bone to install the corresponding prosthesis. During the resection process, the doctor will constantly change the angle of the swing operation according to the actual degree of resection and the prompts of the AI (Artificial Intelligence) planning software to achieve the best resection effect. Bones have different shapes and sizes. The hard compact bone is on the outside, and the porous cancellous bone, also known as spongy bone, is on the inside. Therefore, in the actual resection process, the torque of the swing is constantly changing. The torque and current are in direct proportion, which means that the current is also constantly changing. When encountering hard compact bone, a large current needs to be output at the control end to meet the use requirements, resulting in the entire bone cutting process. The torque and current changes are in a passive state and the robot control cannot be effectively realized.
[0040] In response to the above problems, the present application provides a new intelligent power control solution, which actively controls the implementation of osteotomy under different bone densities by detecting bone density and planning osteotomy information, thereby solving the problem of low osteotomy control accuracy.
[0041] The present application embodiment provides an orthopedic surgical robot intelligent power control method. The specific scheme of the method is as follows: Figure 1-Figure 6 As shown, the method can be performed by an orthopedic surgery robot intelligent power control device, and the orthopedic surgery robot intelligent power control device can be integrated into electronic devices such as computers, servers, computers, server clusters, and data centers. Figure 1 As shown, it is a flow chart of an intelligent power control method for an orthopedic surgical robot according to an embodiment of the present application; wherein the intelligent power control method for an orthopedic surgical robot comprises:
[0042] S100, obtaining a bone medical image of any object;
[0043] In this application, the bone medical image is a CT medical image;
[0044] S200, determining a preoperative planning scheme according to the skeletal medical image, and detecting the bone density of the skeletal medical image;
[0045] S300, determining osteotomy planning information based on the preoperative planning scheme and the bone density;
[0046] In one embodiment, the osteotomy planning information includes an osteotomy path, an osteotomy frequency corresponding to the osteotomy path, and a control current and a control voltage of a terminal power device.
[0047] The osteotomy path is determined according to a preoperative planning scheme, which includes a matching prosthesis model and osteotomy surface. The osteotomy path can be obtained by setting the path of the osteotomy surface.
[0048] In the present application, the osteotomy path refers to the tip path of the end tool when performing osteotomy, and does not include the movement path of the end tool leaving the osteotomy surface.
[0049] S400, controlling the end power device of the orthopedic surgical robot to perform a bone cutting test according to the osteotomy planning information;
[0050] In the present application, the bone cutting test may be a test performed on similar bones or may be actual bone cutting during surgery.
[0051] S500, obtains real-time data of the end power device during the bone cutting test;
[0052] In the present application, the real-time data of the terminal power device includes the real-time position data of the power device, and the real-time swing frequency data or the real-time control voltage and control current of the power device.
[0053] In the present application, the swing frequency of the power device can be read by the internal settings of the power device, or it can be determined by an NDI positioning and navigation device.
[0054] In the present application, the NDI positioning and navigation system uses a linear array CCD lens accurately calibrated by NDI to form a displacement sensor. The CCD is used to capture the near-infrared light actively emitted by the pendulum markers from different angles. Through the precise calculation and analysis inside NDI, the three-dimensional spatial coordinates of each marker at different times can be obtained in real time and accurately. NDI obtains the real-time and precise coordinates of the pendulum and can calculate the vibration frequency of the pendulum. The specific implementation is as follows: the NDI positioning sensor-Position Sensor emits infrared rays for wireless Marker sensing reflection, and the positioning sensor tracks and detects the Marker movement information. The system control unit (SCU) and the hub activate the actively working markers to prompt them to emit infrared rays. The positioning sensor tracks and detects the infrared signals. The positioning sensor (Position Sensor) measures the markers and calculates the changes in the position and direction of the tools attached with the markers. The positioning sensor (Position Sensor) is controlled by the system software. Sensor) inputs the converted data and information into the ToolBox software (for example: if the three-dimensional coordinates of the current pendulum Tx, Ty, and Tz reciprocate between 100 and 120, then the number of swings of the pendulum in the Tx, Ty, and Tz directions can be obtained, and the number of swings within 1 minute is calculated as the swing frequency.
[0055] S600, adjusting the osteotomy planning information according to the real-time data until the osteotomy test is completed.
[0056] In this application, the bone density of the skeletal medical image is used to determine the bone density distribution on the osteotomy path, so that the corresponding osteotomy planning data is pre-set based on the bone density to avoid the lagging swing saw control that cannot accurately control the specific progress of the orthopedic surgical robot.
[0057] In one embodiment, in combination Figure 3 , Figure 5 As shown, the detecting of the bone density of the skeletal medical image includes:
[0058] S201, splitting the skeleton medical image into multiple local medical images;
[0059] In the present application, key points can be set in the image and a local medical image of a preset size can be captured with the key points as the center; or the local medical image can be directly captured in an equal-division manner.
[0060] In the present application, the local medical image is arranged vertically to accommodate the two side boundaries of the bone and avoid the situation where the inside and outside of the bone cannot be identified.
[0061] In the present application, by splitting into local medical images, more local bone densities are obtained, thereby determining the bone density distribution in the skeletal medical image.
[0062] In the present application, the bone density distribution in the skeletal medical image is the bone density distribution in the three-dimensional model of the hip joint.
[0063] S202, inputting a plurality of local medical images into a first detection structure to obtain a medical image of interest;
[0064] In the present application, each local medical image corresponds to a plurality of medical images of interest (ROI), which are images of the segmented bone portion and may further include images of cancellous bone region of interest and images of cortical bone region of interest.
[0065] In this application, by focusing on medical images, the images can be split into parts corresponding to different bone densities, and then the bone density corresponding to each part can be obtained.
[0066] S203, after embedding the medical image of interest into position information, inputting the second detection structure to obtain the bone density corresponding to the medical image of interest and the overall bone density;
[0067] In the present application, the overall bone density is the comprehensive bone density of the local medical image. Each medical image of interest in the local medical image also has its own corresponding bone density.
[0068] S204: Determine the bone density of the skeletal medical image based on the bone density of the medical image of interest and the overall bone density.
[0069] In the present application, the bone density of the skeletal medical image can be obtained by calculating the average value, that is, the average value of the bone density of the medical image and the overall bone density is the bone density of the skeletal medical image.
[0070] In one embodiment, in combination Figure 5 As shown, the step of splitting the skeleton medical image into a plurality of local medical images includes:
[0071] Determine a preset number of special points in the skeleton medical image; and generate a corresponding local medical image based on the special points.
[0072] In the present application, the special points may be evenly set key points, or they may be the femoral condyle, femoral intercondylar fossa, tibial plateau, tibial tuberosity, or points corresponding to the above special points. The corresponding femoral condyle, femoral intercondylar fossa, tibial plateau, and tibial tuberosity (as a local medical image) may be circled through these points, thereby achieving targeted detection of bone density.
[0073] Among them, femoral condyles: The medial and lateral femoral condyles are important components of the knee joint, which contact with the tibial plateau to form the main load-bearing surface of the knee joint.
[0074] Among them, the intercondylar notch is located between the inner and outer femoral condyles, where the cruciate ligaments (anterior cruciate ligament and posterior cruciate ligament) are attached.
[0075] Among them, the tibial plateau (Tibial Plateau): includes the medial and lateral platforms, which are in contact with the femoral condyle and are the main load-bearing surface of the knee joint.
[0076] Among them, the tibial tubercle (Tibial Tuberosity): the site of attachment of the patellar tendon, located on the front side of the tibia.
[0077] In one embodiment, in combination Figure 6 As shown, after embedding the medical image of interest into the position information, inputting into the second detection structure, obtaining the bone density corresponding to the medical image of interest and the overall bone density, including:
[0078] Embedding the medical image of interest into position information to obtain an embedded feature map;
[0079] Normalize the embedded feature map to obtain the corresponding Q key value, K key value, and V key value;
[0080] Input the Q key value, K key value, and V key value into the multi-head attention module to obtain the attention feature map;
[0081] After adding the embedding feature map and the attention feature map, we get the added feature map;
[0082] The added feature map is subjected to normalization processing and multi-layer perception processing in sequence to obtain a multi-layer perception feature map;
[0083] After adding the multi-layer perception feature map and the addition feature map, a first feature map is obtained;
[0084] After the first feature map is processed multiple times according to the processing process of the embedded feature map, an end point feature map is obtained;
[0085] Perform full connection processing on the endpoint feature map to obtain the corresponding bone density;
[0086] Based on the bone density corresponding to the medical image of interest, the overall bone density is determined.
[0087] in, Figure 6 The Norm in it is the normalization layer, MLP is the multi-layer perception processing layer, and FC is the fully connected layer.
[0088] In the present application, there are multiple modules for processing the first feature map from the embedded feature map. The first module processes the embedded feature map to obtain the first feature map; the second module processes the first feature map to obtain the second feature map; and the processing is performed in this way in sequence until the last module processes to obtain the end feature map.
[0089] Among them, the structures of different modules are the same, but the specific parameters are different.
[0090] Among them, the overall bone density is determined based on the bone density corresponding to the medical image of interest. It can be determined comprehensively, for example, a weight is assigned to each medical image of interest, and the overall bone density is obtained by adding the product of the weight and the corresponding bone density.
[0091] In one implementation, after embedding the medical image of interest into position information, inputting the embedded medical image into a second detection structure further includes:
[0092] After the medical image of interest is embedded in the position information, a global extraction process is performed, and the medical image of interest after the global extraction process is input into the second detection structure.
[0093] In this way, better global feature enhancement can be achieved through global extraction.
[0094] Among them, the process of global extraction is:
[0095] The medical image of interest after embedding the position information is used as the input feature map for global extraction;
[0096] Input the input feature map into a 1×1 convolution layer set in parallel to obtain a first extraction map, a second extraction map, and a third extraction map respectively; wherein the first extraction map and the third extraction map are in HW×N format, and the second extraction map is in N×HW format;
[0097] Multiply the first extracted image and the second extracted image to obtain a multiplied feature image;
[0098] Perform softmax processing on the multiplied feature map to obtain the multiplication coefficient;
[0099] Multiplying the multiplication coefficient with the third extraction map to obtain a coefficient multiplication map;
[0100] The coefficient multiplication map and the input medical image of interest are added to obtain the globally extracted output feature map.
[0101] In the present application, the input feature map is divided into three branches for 1×1 convolution processing. The dimensions of the first branch and the third branch are adjusted to HW×N format, and the dimension of the second branch is N×HW format; then the first branch is multiplied by the third branch to obtain a feature map with a dimension of HW×HW, and a coefficient is obtained through softmax processing; the coefficient is multiplied with the third branch, and the multiplied feature map is added to the input feature map to obtain an output feature map.
[0102] In this application, the dimensions of the first branch and the second branch are reversed through 1×1 convolution, thereby realizing multiplication between feature maps; through this multiplication, long-range dependencies are captured; by setting coefficients, the dependencies are embedded in the feature maps; and on this basis, the original input is added and a residual connection is used to embed the global extraction into the model without destroying the parameters.
[0103] In this application, long-range dependencies between features are captured through global extraction, so that the model can extract global features, making up for the defect that the current model mainly extracts local features.
[0104] In the present application, the response at a position is calculated as the weighted sum of the features at all positions, so that when processing the information at each position, the processing is performed on the basis of considering all the position information that can be considered.
[0105] In one embodiment, determining a preoperative planning scheme according to the skeletal medical image includes:
[0106] Perform image segmentation on bone medical images to separate the bone part from the non-bone part;
[0107] Based on the connected domain analysis, the bone segmentation results are subjected to bone extraction to extract the bone structure to be osteotomized;
[0108] Creating a three-dimensional bone image based on the extracted bone structure;
[0109] Key points in the three-dimensional bone image are identified, and an osteotomy planning scheme is determined based on the identified key points.
[0110] In this application, the three-dimensional skeleton key points are identified through the point recognition deep reinforcement learning model. On the one hand, the point recognition deep reinforcement learning model can be trained through the background to reduce the real-time calculation amount; on the other hand, the trained model can be directly used for key point recognition during planning, thereby greatly improving the recognition efficiency.
[0111] It should be noted that the three-dimensional bone key points that need to be identified in this application are determined based on the actual needs when performing prosthesis planning. For example, if only the intercondylar fossa key points are needed to complete the prosthesis planning, then the point identification deep reinforcement learning model is the intercondylar fossa identification deep reinforcement learning model.
[0112] Among them, the medical data of the knee joint is calculated based on the three-dimensional bone key points; the prosthesis model of the knee joint is determined based on the medical data of the knee joint; the prosthesis position of the knee joint and the osteotomy plane posture information are determined according to the prosthesis signal of the knee joint, and the osteotomy plane posture information is determined based on the overlapping position information of the three-dimensional image of the knee joint and the prosthesis of the knee joint.
[0113] In the present application, the medical data of the knee joint are medical data that can determine the position and model of the prosthesis, such as lateral femoral extension gap: the vertical distance from the lateral distal point of the femur to the osteotomy surface; lateral femoral flexion gap: the distance from the lateral posterior condyle point of the femur to the posterior condyle osteotomy surface; medial femoral extension gap: the vertical distance from the medial distal point of the femur to the osteotomy surface; medial femoral flexion gap: the distance from the medial posterior condyle point of the femur to the posterior condyle osteotomy surface; medial tibial extension gap: the distance from the medial point of the tibial plateau to the osteotomy surface; medial tibial flexion gap: the distance from the medial point of the tibial plateau to the osteotomy surface, etc. The specific medical data used can be determined according to actual needs.
[0114] In the present application, the osteotomy plane posture information is determined based on the overlapping position information of the three-dimensional image of the knee joint and the prosthesis of the knee joint, that is, the overlapping position of the three-dimensional image of the knee joint and the prosthesis of the knee joint is used as the part that needs to be cut off, and the boundary of the overlapping position is the osteotomy plane posture information.
[0115] In one embodiment, after acquiring the real-time data of the end power device during the bone cutting test, the method further includes:
[0116] A safety zone is generated based on the osteotomy planning information; after the end power device enters the safety zone, the osteotomy is stopped.
[0117] Among them, the safety measures may also be:
[0118] According to the osteotomy plane posture information of the bone to be osteotomized and the three-dimensional bone model, the osteotomy plane boundary and the soft tissue protection area are generated; the calculation formula of the osteotomy path is determined, the distal end of the road surface is set as the target position, and the soft tissue protection area is set as the gravitational field; the osteotomy plane boundary is set as a strong constraint safety strategy, and multiple waypoints are generated based on the strong constraint safety strategy, and the combination of the waypoints is the planned osteotomy path.
[0119] In this application, the osteotomy plane boundary is set as a strong constraint safety strategy to separate the osteotomy area from the soft tissue protection area, thereby executing path planning under only the gravitational field (the osteotomy plane boundary can also be regarded as a special repulsive field).
[0120] In one embodiment, determining osteotomy planning information based on the preoperative planning scheme and the bone density includes:
[0121] Based on the preoperative planning scheme, determine the osteotomy path;
[0122] Obtain the preset bone density and osteotomy frequency comparison table;
[0123] Based on the bone density distribution on the osteotomy path, determining the osteotomy frequency corresponding to each position on the osteotomy path;
[0124] Based on the built-in parameters of the end power device, the control current and control voltage corresponding to the osteotomy frequency are determined.
[0125] Among them, a comparison table of osteotomy frequency / swing frequency and control current and control voltage is set inside the terminal power device. Based on this comparison table, the control current and control voltage corresponding to the osteotomy frequency can be determined.
[0126] Among them, the bone density and osteotomy frequency comparison table can be obtained in the laboratory or by collecting historical orthopedic surgical robot operation data.
[0127] For example: In the laboratory, animal bones with corresponding bone density are selected and multiple cutting experiments are carried out to determine the osteotomy frequency corresponding to each bone density and establish a comparison table.
[0128] For example: obtaining historical operation data of orthopedic surgical robots, which include the osteotomy path of the end power device, the osteotomy frequency at each position on the osteotomy path, and the medical image of the surgical object; obtaining the bone density distribution at the surgical position and the bone density distribution on the osteotomy path based on the medical image; selecting a path with similar bone density and analyzing the actual osteotomy frequency on the path; if the osteotomy frequency gradually converges to a specific value after fluctuations, then the osteotomy frequency value can be used as the value corresponding to the bone density, so that a bone density and osteotomy frequency comparison table can be established.
[0129] In one embodiment, osteotomy test and intraoperative osteotomy are performed, and the actual osteotomy frequency during osteotomy is recorded; based on the actual osteotomy frequency, the bone density and osteotomy frequency comparison table is continuously iterated through the second example mentioned above, so as to obtain a better bone density and osteotomy frequency comparison table to achieve more accurate control.
[0130] Combination Figure 4 As shown, it is a further example of intelligent power control, which can be specifically:
[0131] Based on the overall analysis of the patient's CT images and bone density images:
[0132] A customized osteotomy plan is developed based on the patient's CT images, bone density images, matching prosthesis models, and the robot's bone cutting action;
[0133] An overall package plan is developed including preoperative planning, osteotomy cutting angle, cutting frequency, progress speed, and osteotomy protection safety area.
[0134] In the process of bone cutting, the load of the traditional pendulum is constantly changing due to the different bone positions, bone cutting depths and angles. The torque is proportional to the current, which means that the current is constantly changing. The current is supplied by a switching power supply. Since there is no closed-loop feedback between the switching power supply and the pendulum, the swing of the pendulum is in a passive state. There is no signal feedback between the pendulum and the switching power supply, and the switching power supply will not actively adjust the swing frequency in real time. In this way, during the bone cutting process, the load changes unstably, and the switching power supply passively outputs different currents. At certain moments, there will be large current changes. Since the pendulum cannot withstand long-term large fluctuations in current, the pendulum will eventually fail or even burn out. Based on this, the device of the present invention will first plan the swing frequency (voltage and current control) used in the bone cutting process in advance based on the bone quality analysis in the preoperative planning software, and through the later real-time compensation function of the optical positioning system, form an overall closed-loop control process to ensure that the bone cutting process is safe and effective.
[0135] Based on the preoperative planning software, the bone cutting process is carried out after analyzing the bone quality. For example, the bone cutting depth at a certain position is 3mm. The 3mm bone cutting depth may be subdivided into 1mm hard compact bone outside and 2mm soft cancellous bone inside. After the preoperative bone analysis, the robot controls the pendulum to output different voltages and currents at different feed distances, thereby controlling the actual pendulum frequency, so as to obtain different cutting methods at different positions.
[0136] The implementation plan is formulated based on the patient's bone cutting situation and the comprehensive planning of cutting angle, cutting amount and cutting depth. The specific implementation is as follows: First, the bone cutting position is planned according to the preoperative planning software (preoperative planning is based on Changmugu AIJOINT software), and then the bone quality (bone density), bone cutting marks, friction, and cutting heat are analyzed by deep algorithm of the bone cutting position. The parameters such as the swing frequency, control voltage, and control current required for cutting bones at different positions during the bone cutting process are obtained and imported into the robot master station Master. After calculation by the master station DSP, the precise control PID parameters are obtained, and the Firmware program is generated to perform the final bone cutting action;
[0137] During the osteotomy process, a safety area for osteotomy needs to be established to prevent accidental removal of some tissues, ligaments and other areas that do not need to be removed during the osteotomy process. The specific implementation plan is as follows: After the osteotomy area is established based on the patient's CT image, a protection area needs to be established around the periphery of the osteotomy. Once the safety area is touched during the osteotomy process, the osteotomy action will be stopped immediately to protect the relevant tissues.
[0138] The data is transmitted to the master station through the EtherCat communication mode of NDI. After receiving the real-time data, the master station enters the robot PID adjustment link. The master station uses the digital PID incremental algorithm to calculate and finally complete the PID closed-loop control steps.
[0139] The present application can effectively control the change of the real-time output current. After adding the device, the output current is more stable and will not experience sudden changes, which may cause damage to related components.
[0140] The control device is integrated in the control box of the robot device and performs EtherCat communication with the robot, and the communication rate can reach 100M / bits.
[0141] In this application, according to the bone cutting position of the preoperative planning software, the pendulum frequency, voltage and current of the pendulum during the bone cutting process are precisely controlled to achieve a precisely controlled bone cutting process;
[0142] In this application, closed-loop control is implemented to avoid the phenomenon of current fluctuation caused by the direct control of the switching power supply due to unstable output, which eventually leads to burning;
[0143] In this application, real-time feedback and calculation of bone cutting are performed, and PID parameters during the swing execution process are compensated and corrected in time to control the swing frequency, control current and control voltage of the cutting.
[0144] An embodiment of the present application provides an orthopedic surgical robot intelligent power control device, which is used to execute the orthopedic surgical robot intelligent power control method described in the above content of the present application. The orthopedic surgical robot intelligent power control device is described in detail below.
[0145] like Figure 7 As shown, the orthopedic surgical robot intelligent power control device comprises:
[0146] An image acquisition module 101 is used to acquire a bone medical image of any object;
[0147] A preoperative planning module 102, which is used to determine a preoperative planning scheme according to the skeletal medical image and detect the bone density of the skeletal medical image;
[0148] An osteotomy planning module 103, which is used to determine osteotomy planning information based on the preoperative planning scheme and the bone density;
[0149] A bone cutting test module 104, which is used to control the end power device of the orthopedic surgical robot to perform a bone cutting test according to the osteotomy planning information;
[0150] The real-time adjustment module 105 is used to obtain the real-time data of the end power device during the osteotomy test; and adjust the osteotomy planning information according to the real-time data until the osteotomy test is completed.
[0151] In one embodiment, the osteotomy planning information includes an osteotomy path, an osteotomy frequency corresponding to the osteotomy path, and a control current and a control voltage of a terminal power device.
[0152] In one embodiment, the preoperative planning module 102 is further configured to:
[0153] The skeletal medical image is split into multiple local medical images; the multiple local medical images are input into a first detection structure to obtain a medical image of interest; after embedding the medical image of interest into position information, the image is input into a second detection structure to obtain the bone density and the overall bone density corresponding to the medical image of interest; based on the bone density and the overall bone density of the medical image of interest, the bone density of the skeletal medical image is determined.
[0154] In one embodiment, the preoperative planning module 102 is further configured to:
[0155] Determine a preset number of special points in the skeleton medical image; and generate a corresponding local medical image based on the special points.
[0156] In one embodiment, the preoperative planning module 102 is further configured to:
[0157] The medical image of interest is embedded with position information to obtain an embedded feature map; the embedded feature map is normalized to obtain corresponding Q key values, K key values, and V key values; the Q key values, K key values, and V key values are input into a multi-head attention module to obtain an attention feature map; the embedded feature map and the attention feature map are added to obtain an added feature map; the added feature map is normalized and multi-layer perception processed in turn to obtain a multi-layer perception feature map; the multi-layer perception feature map and the added feature map are added to obtain a first feature map; the first feature map is processed for multiple cycles according to the processing process of the embedded feature map to obtain an endpoint feature map; the endpoint feature map is fully connected to obtain a corresponding bone density; and the overall bone density is determined based on the bone density corresponding to the medical image of interest.
[0158] In one embodiment, the preoperative planning module 102 is further configured to:
[0159] Perform image segmentation on the bone medical image to separate the bone part from the non-bone part; perform bone extraction on the segmentation result of the bone part based on the connected domain analysis to extract the bone structure to be osteotomized; create a three-dimensional bone image based on the extracted bone structure; identify key points in the three-dimensional bone image, and determine the osteotomy planning plan based on the identified key points.
[0160] In one embodiment, the real-time adjustment module 105 is further used to:
[0161] A safety zone is generated based on the osteotomy planning information; after the end power device enters the safety zone, the osteotomy is stopped.
[0162] The orthopedic surgical robot intelligent power control device provided in the above-mentioned embodiment of the present application has a corresponding relationship with the orthopedic surgical robot intelligent power control method provided in the embodiment of the present application. Therefore, the specific content in the device has a corresponding relationship with the orthopedic surgical robot intelligent power control method. The specific content can refer to the records in the orthopedic surgical robot intelligent power control method, and will not be repeated in this application.
[0163] The orthopedic surgical robot intelligent power control device provided in the above-mentioned embodiments of the present application and the orthopedic surgical robot intelligent power control method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.
[0164] The above describes the internal functions and structure of the intelligent power control device of the orthopedic surgical robot. Figure 8 As shown, in practice, the intelligent power control device of the orthopedic surgical robot can be realized as an electronic device, including: a memory 301 and a processor 303.
[0165] The memory 301 may be configured to store programs.
[0166] In addition, the memory 301 may also be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device, contact data, phone book data, messages, pictures, videos, etc.
[0167] The memory 301 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
[0168] The processor 303 is coupled to the memory 301 and is configured to execute a program in the memory 301 to:
[0169] Acquiring a skeletal medical image of any subject;
[0170] Determine a preoperative planning scheme according to the skeletal medical image, and detect the bone density of the skeletal medical image;
[0171] Determining osteotomy planning information based on the preoperative planning scheme and the bone density;
[0172] According to the osteotomy planning information, controlling the end power device of the orthopedic surgical robot to perform a osteotomy test;
[0173] Obtain real-time data of the end power device during bone cutting test;
[0174] The osteotomy planning information is adjusted according to the real-time data until the osteotomy test is completed.
[0175] In one embodiment, the osteotomy planning information includes an osteotomy path, an osteotomy frequency corresponding to the osteotomy path, and a control current and a control voltage of a terminal power device.
[0176] In one implementation, the processor 303 is further configured to:
[0177] The skeletal medical image is split into multiple local medical images; the multiple local medical images are input into a first detection structure to obtain a medical image of interest; after embedding the medical image of interest into position information, the image is input into a second detection structure to obtain the bone density and the overall bone density corresponding to the medical image of interest; based on the bone density and the overall bone density of the medical image of interest, the bone density of the skeletal medical image is determined.
[0178] In one implementation, the processor 303 is further configured to:
[0179] Determine a preset number of special points in the skeleton medical image; and generate a corresponding local medical image based on the special points.
[0180] In one implementation, the processor 303 is further configured to:
[0181] The medical image of interest is embedded with position information to obtain an embedded feature map; the embedded feature map is normalized to obtain corresponding Q key values, K key values, and V key values; the Q key values, K key values, and V key values are input into a multi-head attention module to obtain an attention feature map; the embedded feature map and the attention feature map are added to obtain an added feature map; the added feature map is normalized and multi-layer perception processed in turn to obtain a multi-layer perception feature map; the multi-layer perception feature map and the added feature map are added to obtain a first feature map; the first feature map is processed for multiple cycles according to the processing process of the embedded feature map to obtain an endpoint feature map; the endpoint feature map is fully connected to obtain a corresponding bone density; and the overall bone density is determined based on the bone density corresponding to the medical image of interest.
[0182] In one implementation, the processor 303 is further configured to:
[0183] Perform image segmentation on the bone medical image to separate the bone part from the non-bone part; perform bone extraction on the segmentation result of the bone part based on the connected domain analysis to extract the bone structure to be osteotomized; create a three-dimensional bone image based on the extracted bone structure; identify key points in the three-dimensional bone image, and determine the osteotomy planning plan based on the identified key points.
[0184] In one implementation, the processor 303 is further configured to:
[0185] A safety zone is generated based on the osteotomy planning information; after the end power device enters the safety zone, the osteotomy is stopped.
[0186] In the present application, the processor is also specifically used to execute all processes and steps of the above-mentioned orthopedic surgical robot intelligent power control method. The specific content can be referred to the records in the orthopedic surgical robot intelligent power control method, and will not be repeated in this application.
[0187] In this application, Figure 8 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 8 Components shown.
[0188] The electronic device provided in this embodiment is based on the same inventive concept as the intelligent power control method for an orthopedic surgical robot provided in the embodiment of the present application, and has the same beneficial effects as the method adopted, run or implemented by the application program stored therein.
[0189] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0190] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0191] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0192] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0193] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0194] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0195] The present application also provides a computer-readable storage medium corresponding to the orthopedic surgical robot intelligent power control method provided in the aforementioned embodiment, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the orthopedic surgical robot intelligent power control method provided in any of the aforementioned embodiments.
[0196] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0197] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the orthopedic surgical robot intelligent power control method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.
[0198] It should be noted that in the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known structures and technologies are not shown in detail so as not to obscure the understanding of this description.
[0199] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0200] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. An intelligent power control method for an orthopedic surgical robot, It is characterized in that include: Acquiring a skeletal medical image of any subject; Determine a preoperative planning scheme according to the skeletal medical image, and detect the bone density of the skeletal medical image; Determining osteotomy planning information based on the preoperative planning scheme and the bone density; According to the osteotomy planning information, controlling the end power device of the orthopedic surgical robot to perform a osteotomy test; Obtain real-time data of the end power device during bone cutting test; The osteotomy planning information is adjusted according to the real-time data until the osteotomy test is completed.
2. The intelligent power control method for an orthopedic surgical robot according to claim 1, It is characterized in that The osteotomy planning information includes an osteotomy path, an osteotomy frequency corresponding to the osteotomy path, and a control current and a control voltage of a terminal power device.
3. The intelligent power control method for an orthopedic surgical robot according to claim 1, It is characterized in that The step of detecting the bone density of the skeletal medical image comprises: Splitting the skeleton medical image into multiple local medical images; Inputting a plurality of local medical images into a first detection structure to obtain a medical image of interest; After embedding the medical image of interest into position information, the position information is input into a second detection structure to obtain the bone density corresponding to the medical image of interest and the overall bone density; The bone density of the skeletal medical image is determined based on the bone density of the medical image of interest and the overall bone density.
4. The intelligent power control method for an orthopedic surgical robot according to claim 3, It is characterized in that The step of splitting the skeleton medical image into a plurality of local medical images comprises: determining a preset number of special points in the bone medical image; A corresponding local medical image is generated based on the special point.
5. The intelligent power control method for an orthopedic surgical robot according to claim 3, It is characterized in that After embedding the medical image of interest into the position information, inputting into a second detection structure to obtain the bone density corresponding to the medical image of interest and the overall bone density includes: Embedding the medical image of interest into position information to obtain an embedded feature map; Normalize the embedded feature map to obtain the corresponding Q key value, K key value, and V key value; Input the Q key value, K key value, and V key value into the multi-head attention module to obtain the attention feature map; After adding the embedding feature map and the attention feature map, we get the added feature map; The added feature map is subjected to normalization processing and multi-layer perception processing in sequence to obtain a multi-layer perception feature map; After adding the multi-layer perception feature map and the addition feature map, a first feature map is obtained; After the first feature map is processed multiple times according to the processing process of the embedded feature map, an end point feature map is obtained; Perform full connection processing on the endpoint feature map to obtain the corresponding bone density; Based on the bone density corresponding to the medical image of interest, the overall bone density is determined.
6. The intelligent power control method for an orthopedic surgical robot according to claim 1, It is characterized in that Determining a preoperative planning scheme according to the skeletal medical image comprises: Perform image segmentation on bone medical images to separate the bone part from the non-bone part; Based on the connected domain analysis, the bone segmentation results are subjected to bone extraction to extract the bone structure to be osteotomized; Creating a three-dimensional bone image based on the extracted bone structure; Key points in the three-dimensional bone image are identified, and an osteotomy planning scheme is determined based on the identified key points.
7. The intelligent power control method for an orthopedic surgical robot according to claim 2, It is characterized in that The step of determining osteotomy planning information based on the preoperative planning scheme and the bone density includes: Based on the preoperative planning scheme, determine the osteotomy path; Obtain the preset bone density and osteotomy frequency comparison table; Based on the bone density distribution on the osteotomy path, determining the osteotomy frequency corresponding to each position on the osteotomy path; Based on the built-in parameters of the end power device, the control current and control voltage corresponding to the osteotomy frequency are determined.
8. An intelligent power control device for an orthopedic surgical robot, It is characterized in that include: An image acquisition module, which is used to acquire a bone medical image of any object; A preoperative planning module, which is used to determine a preoperative planning scheme according to the skeletal medical image and detect the bone density of the skeletal medical image; An osteotomy planning module, which is used to determine osteotomy planning information based on the preoperative planning scheme and the bone density; A bone cutting test module, which is used to control the end power device of the orthopedic surgical robot to perform a bone cutting test according to the osteotomy planning information; The real-time adjustment module is used to obtain real-time data of the end power device during the bone cutting test; and adjust the bone cutting planning information according to the real-time data until the bone cutting test is completed.
9. An electronic device, It is characterized in that include: Memory and processor; The memory is used to store programs; The processor, coupled to the memory, is configured to execute the program to: Acquiring a skeletal medical image of any subject; Determine a preoperative planning scheme according to the skeletal medical image, and detect the bone density of the skeletal medical image; Determining osteotomy planning information based on the preoperative planning scheme and the bone density; According to the osteotomy planning information, controlling the end power device of the orthopedic surgical robot to perform a osteotomy test; Obtain real-time data of the end power device during bone cutting test; The osteotomy planning information is adjusted according to the real-time data until the osteotomy test is completed.
10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that The program is executed by the processor to implement the intelligent power control method for an orthopedic surgical robot as described in any one of claims 1-7.
Citation Information
Patent Citations
Intelligent power control method, device and system for orthopedic surgery robot
CN115486940A
Multi-stage image description device with sparsity
CN116935386A
Bone mineral density measurement method and device based on deep learning
CN117838176A
Cited By
Surgical robot control method, device, equipment, medium and product
CN120477943A
